CN116818233A - High-precision bridge state monitoring method and system adopting laser and machine vision - Google Patents
High-precision bridge state monitoring method and system adopting laser and machine vision Download PDFInfo
- Publication number
- CN116818233A CN116818233A CN202310722342.3A CN202310722342A CN116818233A CN 116818233 A CN116818233 A CN 116818233A CN 202310722342 A CN202310722342 A CN 202310722342A CN 116818233 A CN116818233 A CN 116818233A
- Authority
- CN
- China
- Prior art keywords
- bridge
- image
- spot
- laser
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims abstract description 9
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims abstract description 6
- 230000006740 morphological transformation Effects 0.000 claims abstract description 3
- 238000012545 processing Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 9
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 9
- 230000036541 health Effects 0.000 abstract description 2
- 238000000691 measurement method Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Abstract
The application provides a high-precision bridge health state monitoring method and system adopting laser and machine vision, wherein an industrial camera is used for collecting a scale map, and affine transformation correction, denoising, defogging, binarization and morphological transformation are carried out after an effective area containing scale scales and laser spots in a collected color spot image is extracted to obtain a binarized image of the spot; extracting a color spot image by using a binary image, performing an unsaturated point gray information Gaussian fitting method on the spot image, solving a centroid coordinate of a laser spot in an image coordinate system, obtaining a spot centroid variation by making a difference with an initially obtained spot centroid ordinate, obtaining actual disturbance of a bridge through a pixel-to-reality conversion matrix, uploading the actual disturbance to a cloud server through an ftp protocol, combining temperature and humidity data of a bridge monitoring site by the cloud server, generating an instantaneous and continuous bad state threshold of the bridge, and performing early warning. The application has the advantages of simple operation, high measurement precision, less hardware equipment resources and the like.
Description
Technical Field
The application relates to a remote non-contact measurement technology, in particular to a high-precision bridge state monitoring method and system adopting laser and machine vision.
Background
Measurement techniques hold great importance in modern society where mechanized equipment is highly concentrated. However, the current requirements for measuring equipment not only require high precision, high efficiency and strong environment adaptability, but also require the measuring equipment to be convenient and smart, high in automation degree, low in cost and the like. In the bridge deflection detection scene, the requirements of long-time detection, all-weather detection and the like often exist, and the requirements of all aspects are difficult to be met by the traditional measurement method. Therefore, the method has great significance in exploring and researching the automatic, high-precision, real-time and long-distance non-contact novel bridge deflection monitoring and measuring method.
Non-contact measurement methods generally include acoustic wave measurement, photoelectric measurement, radar measurement, etc., where a relatively large number of acoustic wave measurement techniques and photoelectric measurement techniques are used at present, but these two measurement techniques have some limitations, and they both require relatively high requirements for certain physical properties of the measurement object, or otherwise difficult to obtain measurement results. However, although the radar measurement method has high accuracy, the radar measurement method has high requirements on the measurement object and often has high cost.
Disclosure of Invention
The application aims to provide a high-precision bridge state monitoring method and system adopting laser and machine vision.
The technical scheme for realizing the application is as follows: a high-precision bridge state monitoring method adopting laser and machine vision comprises the following steps:
step 1, installing a laser module box on the side surface of a bridge pier, installing an observation camera bellows provided with a light supplementing light source, a graduated scale, an industrial camera and a bracket on the side surface of the center of the bridge deck, wherein the graduated scale is opposite to an industrial camera, so that laser light can vertically enter the graduated scale, the initial position of a target light spot is positioned at a 0 scale mark of the graduated scale, acquiring a graduated scale image by the industrial camera, and when the deflection of the bridge is changed, the position of the laser light spot is changed;
step 2, extracting an effective area containing scale marks and laser spots in the acquired color spot images by the on-site working condition machine, and then carrying out affine transformation correction; denoising, defogging, binarizing and morphological transformation are carried out on the color facula image to obtain a binarized image of the facula; extracting a colored spot image by using a binary image, performing an unsaturated point gray information Gaussian fitting method on the colored spot image, solving a centroid coordinate of a laser spot in an image coordinate system, performing difference between the obtained centroid of the spot and an initially obtained centroid ordinate of the spot to obtain a centroid variation of the spot, and obtaining actual disturbance of a bridge through a pixel-to-reality conversion matrix;
and 3, superposing the actual disturbance of the bridge on the real-time image, uploading the actual disturbance of the bridge to a cloud server through an ftp protocol, combining the temperature and humidity data of the bridge monitoring site by the cloud server, generating an instantaneous and continuous bad state threshold value of the bridge, and carrying out early warning when the bridge disturbance exceeds the instantaneous threshold value or the bridge exceeds the continuous threshold value within a period of time.
And (3) affine transformation correction, namely shooting a group of black and white chessboard image data by using a camera, calculating an internal and external parameter matrix of the camera according to the contrast between the black and white square distance on the shot image and the actual distance, and correcting the distortion of the camera.
The denoising adopts bilateral filtering, and a template formula of the bilateral filtering is as follows:
wherein (i, j) is the coordinates of the center pixel of the template window; (k, l) is the coordinates of the other pixels of the template window; sigma (sigma) d Sum sigma r Standard deviation of Gaussian functions of the airspace template and the value domain template respectively; f (i, j) is the gray value of the target point before processing.
The defogging adopts a dark channel defogging formula:
wherein k represents a point coordinate in the image, c is one of three color channels of r, g and b, J c To process the pre-image, J dark For processing the post-image, w k Is a rectangular window centered on k.
The binarization is carried out, the color image is converted into a gray image through a matrix, the pixels with the brightness value larger than the judging threshold value are selected to be marked as white, and other pixels are marked as black, wherein the conversion formula for converting the color image into the gray image is as follows:
wherein Y represents the brightness value of the image, and R, G and B are three channel values of the input image;
the threshold value is an empirical value, and the method for determining the threshold value is specifically to observe that the illumination condition in the camera bellows is stable, and the brightness of the background and the graduated scale in the facula image shot by the industrial camera is almost unchanged, so 180 is selected as the threshold value.
The morphological processing utilizes structural elements to perform morphological filtering on the binary image, and the specific formula is as follows:
wherein B' is the binary image after the treatment, B is the binary image before the treatment, S is the structural element of a 3X 3 white square, and the sum of the twoRepresenting corrosion and expansion operations, respectively.
The unsaturated point gray information Gaussian fitting method takes the upper left corner of an image as an original point, takes the right corner as the positive direction of the x axis, takes the downward direction as the positive direction of the y axis, and obtains the center coordinate of a laser spot in an image coordinate system through the unsaturated point gray information Gaussian fitting method for the preprocessed binary spot image, wherein the formula is as follows:
wherein x and y are respectively the horizontal and vertical coordinates of the center, and x 1 、x 2 、x 3 Is the abscissa, y of any three pixel points with the same ordinate and different abscissas on the light spot 1 、y 2 、y 3 G represents the gray value of the pixel point for the ordinate of any three pixel points with the same abscissa and different ordinate on the light spot;
and weighting according to the distance between each spot pixel and the center to obtain the spot centroid.
The bridge deflection comprises the following calculation formula:
s＝scale·Δy＝scale·(y 1 -y 0 )
wherein s is bridge deflection, scale is pixel scale, i.e. the actual length corresponding to the size of a single pixel, y 1 And y 0 The current light spot centroid ordinate and the reference light spot centroid ordinate are respectively, and deltay is the light spot centroid displacement.
The bad state threshold value of the bridge disturbance is calculated according to the following formula:
wherein b is an empirical constant value, 1.5762 is taken, sigma is the average structural coefficient of the bridge, t i Is the real-time temperature of the bridge, t o Is a bridgeAverage temperature, RH of the region i Real-time humidity, RH, of bridges o The average humidity of the area where the bridge is located,is the average value of bridge disturbance at the same load in the past.
The high-precision bridge state monitoring system implements the high-precision bridge state monitoring method adopting laser and combining machine vision, and realizes high-precision bridge state monitoring.
Compared with the prior art, the application has the remarkable advantages that: (1) The red laser spot is identified to fall on the graduated scale, and the ordinate of the centroid of the spot and the ordinate of the reference centroid have higher precision and are less influenced by the outside; (2) Different thresholds are automatically generated through cloud big data, so that bridge disturbance can better reflect the health condition of the bridge, and management staff can overhaul and maintain the bridge in time; (3) The system can automatically complete the whole process, has high automation, strong real-time performance and simple and convenient operation; (4) The required hardware equipment resources are few, the bridge deflection is convenient to monitor for a long time, and the cost is low.
Drawings
FIG. 1 is a schematic diagram of a high-precision single-point bridge deflection monitoring method by combining laser reference with image processing.
FIG. 2 is a general frame diagram of a high-precision single-point bridge deflection monitoring method of the laser reference combined with image processing.
FIG. 3 is a flow chart of a method for monitoring deflection of a high-precision single-point bridge by combining laser reference with image processing.
Fig. 4 is a laser spot diagram of the high-precision single-point bridge deflection monitoring method combining laser reference with image processing.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The application discloses a high-precision single-point bridge deflection monitoring method by combining laser reference with image processing, which comprises the following steps of:
step 1, a cuboid laser module box provided with a red laser is arranged on a bridge pier, a cuboid observation camera bellows provided with a light supplementing light source, a graduated scale, an industrial camera and a bracket is arranged on the side surface of the bridge, wherein the graduated scale is opposite to the industrial camera, so that the light of the laser can vertically enter the graduated scale, and the initial position of a target light spot is positioned at a 0 graduation line of the graduated scale; acquiring a graduated scale image by using an industrial camera, and changing the position of a laser spot when the deflection of the bridge changes; the cuboid laser module box and the cuboid observation camera bellows are respectively provided with rectangular openings on the side walls of one side of each of the cuboid laser module box and the cuboid observation camera bellows, and the other five sides are opaque.
Step 2, extracting an effective area containing scale marks and laser spots in the acquired color image by the on-site working condition machine, and then carrying out affine transformation correction; performing bilateral filtering and dark channel prior defogging on the color facula image to obtain a noise-reduced color image, performing color recognition and threshold judgment on the noise-reduced image to obtain a binary image of the facula, and performing morphological processing on the binary image of the facula to obtain a preprocessed binary facula image;
affine transformation correction is to shoot a group of black and white checkerboard image data by using a camera, calculate an internal and external parameter matrix of the camera according to the contrast between the black and white checkerboard distance on the shot image and the actual distance, and correct the distortion of the camera.
The template formula of the bilateral filtering is as follows:
wherein (i, j) is the coordinates of the center pixel of the template window; (k, l) is the coordinates of the other pixels of the template window; sigma (sigma) d Sum sigma r Standard deviation of Gaussian functions of the airspace template and the value domain template respectively; f (i, j) is the processing frontGray value of punctuation;
the dark channel defogging formula is as follows:
wherein k represents a point coordinate in the image, c is one of three color channels of r, g and b, J c To process the pre-image, J dark For processing the post-image, w k A rectangular window centered on k;
the color recognition and threshold judgment are specifically to convert a color image into a gray image through a matrix, wherein pixels with brightness values larger than a judgment threshold are selected to be marked as white, and other pixels are marked as black. The conversion formula in which a color image is converted into a grayscale image is as follows:
wherein Y represents the brightness value of the image, and R, G and B are three channel values of the input image;
the threshold value is an empirical value, and the method for determining the threshold value is specifically to observe that the illumination condition in the camera bellows is stable, and the brightness of the background and the graduated scale in the facula image shot by the industrial camera is almost unchanged, so 180 is selected as the threshold value.
The morphological processing method is that structural elements are utilized to perform morphological filtering on the binary image, and the specific formula is as follows:
wherein B' is the binary image after treatment, B is the binary image before treatment, S is the structural element of a 3X 3 white square, and the sum of the twoRepresenting corrosion and expansion operations, respectively.
Step 3, extracting a colored spot image by using a binary image, taking the upper left corner of the collected colored image as an original point, taking the right corner as an x-axis positive direction, taking the downward corner as a y-axis positive direction, carrying out an unsaturated point gray level information Gaussian fitting method on the colored spot image to obtain a theoretical light spot center, and carrying out weighting according to the distance between each light spot pixel and the center to obtain a light spot centroid;
the formula of the unsaturated point gray information Gaussian fitting method is as follows:
wherein, x and y are respectively the horizontal and vertical coordinates of the center, x 1 ，x 2 ，x 3 The y is the abscissa of any three pixel points with the same ordinate and different abscissas on the light spot 1 ，y 2 ，y 3 And g represents the gray value of the pixel point to be taken, wherein the gray value is the ordinate of the pixel point with the same arbitrary three abscissas and different abscissas on the light spot.
Step 4, calibrating a reference spot coordinate, and differencing the ordinate of the centroid of the spot from the ordinate of the reference centroid, when the deflection of the bridge changes, the position of the laser spot changes, and the change of the spot position coordinate is recorded, namely the actual deflection of the bridge;
the calculation formula of the deflection of the bridge is as follows:
s＝scale·Δy＝scale·(y 1 -y 0 )
wherein s is bridge deflection, scale is pixel scale, i.e. the actual length corresponding to the size of a single pixel, y 1 And y 0 The current light spot centroid ordinate and the reference light spot centroid ordinate are respectively, and deltay is the light spot centroid displacement.
And 5, acquiring a real-time image of the bridge safety key parameter including bridge disturbance by means of a machine vision technology, superposing the measured data on the real-time image and uploading the real-time image to a cloud server, and enabling bridge management personnel to access the server through a PC-end web page or a mobile phone-end APP so as to acquire the acquired field image and the measured data. After the received bridge disturbance, the cloud server can combine the temperature, the humidity and the disturbance data in the past of the bridge to generate an instantaneous and continuous bad state threshold value of the bridge, and when the bridge exceeds the instantaneous threshold value or the bridge exceeds the continuous threshold value for a period of time, a warning is sent to remind a manager to overhaul and maintain.
The solving formula of the bad state threshold value of the bridge disturbance is as follows:
the above formula is an empirical formula which is an empirical summary based on measured data, where t i Is the real-time temperature of the bridge, t o Is the average temperature, RH, of the area where the bridge is located i Real-time humidity, RH, of bridges o Average humidity of the area where the bridge is located.
The measured data is uploaded to the cloud for storage, so that the memory requirement of the field computing equipment is reduced on one hand; on the other hand, bridge manager accesses the server through the PC end web page or the mobile end APP, so that acquisition of the acquired field image and measurement data is realized, and manual operation and field observation are not required. The data is acquired from the database without manual update, and after the data is transmitted into the database in the monitoring site, the data of the web page end and the APP are automatically refreshed. The method can realize backtracking inquiry and analysis of the disturbance data in a certain period of the bridge, and after a time interval to be inquired is selected, the result is presented in a graph mode, and a manager can clearly see the change condition of the disturbance data of the bridge, and the maximum value, the minimum value and the middle value of deflection data in the period of time. Meanwhile, the system also collects temperature and humidity data of the bridge monitoring site, and generates an instantaneous and continuous bad state threshold value of the bridge by combining design parameters of a specific bridge and disturbance data of the bridge.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. The high-precision bridge state monitoring method adopting laser and machine vision is characterized by comprising the following steps of:
step 1, installing a laser module box on the side surface of a bridge pier, installing an observation camera bellows provided with a light supplementing light source, a graduated scale, an industrial camera and a bracket on the side surface of the center of the bridge deck, wherein the graduated scale is opposite to an industrial camera, so that laser light can vertically enter the graduated scale, the initial position of a target light spot is positioned at a 0 scale mark of the graduated scale, acquiring a graduated scale image by the industrial camera, and when the deflection of the bridge is changed, the position of the laser light spot is changed;
step 2, extracting an effective area containing scale marks and laser spots in the acquired color spot images by the on-site working condition machine, and then carrying out affine transformation correction; denoising, defogging, binarizing and morphological transformation are carried out on the color facula image to obtain a binarized image of the facula; extracting a colored spot image by using a binary image, performing an unsaturated point gray information Gaussian fitting method on the colored spot image, solving a centroid coordinate of a laser spot in an image coordinate system, performing difference between the obtained centroid of the spot and an initially obtained centroid ordinate of the spot to obtain a centroid variation of the spot, and obtaining actual disturbance of a bridge through a pixel-to-reality conversion matrix;
and 3, superposing the actual disturbance of the bridge on the real-time image, uploading the actual disturbance of the bridge to a cloud server through an ftp protocol, combining the temperature and humidity data of the bridge monitoring site by the cloud server, generating an instantaneous and continuous bad state threshold value of the bridge, and carrying out early warning when the bridge disturbance exceeds the instantaneous threshold value or the bridge exceeds the continuous threshold value within a period of time.
2. The method for monitoring the bridge state with high precision by combining laser with machine vision according to claim 1, wherein affine transformation is corrected, a group of black and white chessboard image data is shot by using a camera, an internal and external parameter matrix of the camera is calculated according to the contrast between the black and white square distance on the shot image and the actual distance, and the distortion of the camera is corrected.
3. The method for monitoring the deflection of the high-precision single-point bridge by combining the laser reference with the image processing according to claim 1, wherein the denoising adopts bilateral filtering, and a template formula of the bilateral filtering is as follows:
wherein (i, j) is the coordinates of the center pixel of the template window; (k, l) is the coordinates of the other pixels of the template window; sigma (sigma) d Sum sigma r Standard deviation of Gaussian functions of the airspace template and the value domain template respectively; f (i, j) is the gray value of the target point before processing.
4. The method for monitoring the state of the bridge with high precision by combining laser with machine vision according to claim 1, wherein the defogging adopts a dark channel defogging formula:
wherein k represents a point coordinate in the image, c is one of three color channels of r, g and b, J c In order to process the pre-image,J dark for processing the post-image, w k Is a rectangular window centered on k.
5. The method for monitoring the bridge state with high precision by combining laser and machine vision according to claim 1, wherein the binarization is used for converting a color image into a gray image through a matrix, the pixels with the brightness value larger than a judgment threshold value are selected to be marked as white, and the other pixels are marked as black, wherein the conversion formula for converting the color image into the gray image is as follows:
wherein Y represents the brightness value of the image, and R, G and B are three channel values of the input image;
the threshold value is an empirical value, and the method for determining the threshold value is specifically to observe that the illumination condition in the camera bellows is stable, and the brightness of the background and the graduated scale in the facula image shot by the industrial camera is almost unchanged, so 180 is selected as the threshold value.
6. The method for monitoring the state of the bridge with high precision by combining laser with machine vision according to claim 1, wherein the morphological processing utilizes structural elements to perform morphological filtering on the binary image, and the specific formula is as follows:
wherein B' is the binary image after the treatment, B is the binary image before the treatment, S is the structural element of a 3X 3 white square, and the sum of the twoRepresenting corrosion and expansion operations, respectively.
7. The method for monitoring the state of the bridge with the high precision by combining the laser with the machine vision according to claim 1, wherein the unsaturated point gray information Gaussian fitting method is characterized in that an upper left corner of an image is taken as an original point, a right corner is taken as an x-axis positive direction, a downward direction is taken as a y-axis positive direction, and a central coordinate of a laser spot in an image coordinate system is obtained by the preprocessed binary spot image through the unsaturated point gray information Gaussian fitting method, wherein the formula is as follows:
wherein x and y are respectively the horizontal and vertical coordinates of the center, and x 1 、x 2 、x 3 Is the abscissa, y of any three pixel points with the same ordinate and different abscissas on the light spot 1 、y 2 、y 3 G represents the gray value of the pixel point for the ordinate of any three pixel points with the same abscissa and different ordinate on the light spot;
and weighting according to the distance between each spot pixel and the center to obtain the spot centroid.
8. The method for monitoring the state of the bridge with high precision by combining laser with machine vision according to claim 1, wherein the bridge deflection is calculated according to the following formula:
s＝scale·Δy＝scale·(y 1 -y 0 )
wherein s is bridge deflection, scale is pixel scale, i.e. the actual length corresponding to the size of a single pixel, y 1 And y 0 The current light spot centroid ordinate and the reference light spot centroid ordinate are respectively, and deltay is the light spot centroid displacement.
9. The method for monitoring the state of the bridge with high precision by combining laser with machine vision according to claim 1, wherein the bad state threshold of the bridge disturbance is calculated according to the following formula:
wherein b is an empirical constant value, 1.5762 is taken, sigma is the average structural coefficient of the bridge, t i Is the real-time temperature of the bridge, t o Is the average temperature, RH, of the area where the bridge is located i Real-time humidity, RH, of bridges o The average humidity of the area where the bridge is located,is the average value of bridge disturbance at the same load in the past.
10. A high-precision bridge state monitoring system, characterized in that the high-precision bridge state monitoring method adopting laser and machine vision according to any one of claims 1-9 is implemented to realize high-precision bridge state monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310722342.3A CN116818233A (en) | 2023-06-16 | 2023-06-16 | High-precision bridge state monitoring method and system adopting laser and machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310722342.3A CN116818233A (en) | 2023-06-16 | 2023-06-16 | High-precision bridge state monitoring method and system adopting laser and machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116818233A true CN116818233A (en) | 2023-09-29 |
Family
ID=88113929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310722342.3A Pending CN116818233A (en) | 2023-06-16 | 2023-06-16 | High-precision bridge state monitoring method and system adopting laser and machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116818233A (en) |
-
2023
- 2023-06-16 CN CN202310722342.3A patent/CN116818233A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021093283A1 (en) | Sea surface small-area oil spill region detection system and detection method based on multi-sensing fusion | |
| CN110108348B (en) | Thin-wall part micro-amplitude vibration measurement method and system based on motion amplification optical flow tracking | |
| CN105574897A (en) | Crop growth situation monitoring Internet of Things system based on visual inspection | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN104700395A (en) | Method and system for detecting appearance crack of structure | |
| CN113358231B (en) | Infrared temperature measurement method, device and equipment | |
| CN103617611A (en) | Automatic threshold segmentation detection method for center and size of light spot | |
| CN113554667B (en) | Three-dimensional displacement detection method and device based on image recognition | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN112927233A (en) | Marine laser radar and video combined target capturing method | |
| CN113469178A (en) | Electric power meter identification method based on deep learning | |
| CN112634179B (en) | Camera shake prevention power transformation equipment image change detection method and system | |
| Liu et al. | Image-based recognition and processing system for monitoring water levels in an irrigation and drainage channel | |
| CN116818233A (en) | High-precision bridge state monitoring method and system adopting laser and machine vision | |
| CN107194923B (en) | Ultraviolet image diagnosis method for defect inspection of contact network power equipment | |
| GB2470741A (en) | Liquid level detection method | |
| CN112906095B (en) | Bridge modal identification method and system based on laser stripe center tracking | |
| CN107796323A (en) | A kind of micro- change detecting system of bridge based on hot spot vision signal intellectual analysis | |
| CN112966594A (en) | Environment sensing method | |
| CN113536895A (en) | Disc pointer meter identification method | |
| CN113250914A (en) | 2D displacement measurement method, system, equipment and storage medium for cabin tower top | |
| KR20120000036A (en) | Surveying system using a measuring rule | |
| CN117333675B (en) | Monitoring and early warning method and system for GIS expansion joint | |
| CN113971679B (en) | Ocean tide measuring method based on computer vision and image processing | |
| CN114913316B (en) | Image classification method and device for meter recognition of industrial equipment, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |